Instructions to use LinkSoul/Chinese-LLaVA-Baichuan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LinkSoul/Chinese-LLaVA-Baichuan with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="LinkSoul/Chinese-LLaVA-Baichuan")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("LinkSoul/Chinese-LLaVA-Baichuan")
model = AutoModelForCausalLM.from_pretrained("LinkSoul/Chinese-LLaVA-Baichuan")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LinkSoul/Chinese-LLaVA-Baichuan with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LinkSoul/Chinese-LLaVA-Baichuan"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LinkSoul/Chinese-LLaVA-Baichuan",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LinkSoul/Chinese-LLaVA-Baichuan

SGLang

How to use LinkSoul/Chinese-LLaVA-Baichuan with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "LinkSoul/Chinese-LLaVA-Baichuan" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LinkSoul/Chinese-LLaVA-Baichuan",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "LinkSoul/Chinese-LLaVA-Baichuan" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LinkSoul/Chinese-LLaVA-Baichuan",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LinkSoul/Chinese-LLaVA-Baichuan with Docker Model Runner:
```
docker model run hf.co/LinkSoul/Chinese-LLaVA-Baichuan
```

Chinese LLaVA

开源，可商用的中英文双语视觉-语言助手 Chinese-LLaVA 以及中英文视觉 SFT 数据集 Chinese-LLaVA-Vision-Instructions，支持中英文视觉-文本多模态对话的开源可商用对话模型。

基础演示

在线试玩

Talk is cheap, Show you the Demo.

Demo 地址 / HuggingFace Spaces

资源下载

模型：
- Chinese-LLaVA-Chinese-Llama-2-7B
- Chinese-LLaVA-Baichuan-7B
百度网盘下载:
- Chinese-LLaVA-Chinese-Llama-2-7B
- Chinese-LLaVA-Baichuan-7B
语言模型:
- Chinese-Llama-2-7b
- Baichuan-7B
数据集：Chinese-LLaVA-Vision-Instructions

环境安装

# clone the repository
git clone https://github.com/LinkSoul-AI/Chinese-LLaVA
cd Chinese-LLaVA

# install package
conda create -n Cllava python=3.10 -y
conda activate Cllava
pip install --upgrade pip
pip install -e .

快速测试

python infer.py \
    --model-name PATH/TO/THE/CHINESE_LLAVA_MODEL \
    --llm-type "Chinese_llama2" or "baichuan" \
    --image-file PATH/TO/THE/INPUT/IMAGE \
    --query QUERY/PROMPT

TODO

如何训练
int4 量化
docker 部署

项目协议

Apache-2.0 license

微信交流群

欢迎加入微信群

Downloads last month: 19

LinkSoul
/

Chinese-LLaVA-Baichuan